© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4724
    Prev
    Next
    INDEX
    Explanations

    references to ecological diversity and campus-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atorio
    -0.76
    parsedMessage
    -0.76
     وتسجيلات
    -0.74
    м
    -0.71
     Hanne
    -0.68
     epileptic
    -0.67
    laravel
    -0.66
    allowance
    -0.66
     nắm
    -0.64
     Comparator
    -0.62
    POSITIVE LOGITS
     campuses
    0.93
    fully
    0.92
     campus
    0.85
     myſelf
    0.84
    elenco
    0.84
     csal
    0.83
     ſever
    0.82
    universo
    0.82
    fulness
    0.80
     youth
    0.79
    Activations Density 0.079%

    No Known Activations